Sr. Software Engineer, Kernels/CUDA (C++)
Location: Palo Alto, CA · Category: Engineering & Development · Seniority: Senior · Posted: November 6, 2026 · Verified: Nov 16, 2026
Role Overview & Description
Track team expansion and market signals for X
Polaris7 monitors open roles, strategic market movements, and M&A developments in real time. Get automated intelligence briefings on X and benchmark against direct competitors.
Operator of X, a social platform monetised through ads, subscriptions and API access.
Unlock full company profile, competitors & live market signals for X
Similar Positions in DACH
Related roles across advertising, media, and data
This Kernel Engineer role involves designing, implementing, and maintaining high-performance kernels to optimize throughput and latency during training and inference of long-context models. The position requires deep expertise in low-level programming for AI accelerators like NVIDIA Blackwell or Google TPUs, and experience with frameworks such as NCCL, CUTLASS, Triton, and Flash-Attention. The role includes ownership of kernel design, deployment, and production reliability, as well as evaluating porting kernels to alternative hardware.
This senior role leads development of CUDA kernels and GPU optimization for SpaceX's ML infrastructure. The engineer will architect kernel libraries, mentor junior developers, and drive performance improvements across training and inference pipelines. Requires extensive C++ and CUDA expertise.
This Kernel Engineer role at an AI company focuses on making machine learning training and inference faster, more efficient, and more reliable at the hardware-software boundary. The engineer will specialize in GPU/accelerator kernels, ML compilers, or framework/runtime and inference performance, optimizing compute primitives, memory layouts, and code generation. The role requires deep implementation-level expertise in stacks like CUDA, Triton, XLA, or PyTorch/JAX backends.
This Senior Software Engineer role builds and scales ML-optimized HPC infrastructure, deploying and managing Kubernetes-based GPU/TPU superclusters across multiple clouds. The engineer optimizes for AI/ML training with technologies like RDMA and NCCL, troubleshoots complex infrastructure issues, and enables researchers with self-service tools. Requires deep experience with Kubernetes, HPC, and distributed training, plus participation in a 24x7 on-call rotation.
More Positions at X
3 more open roles
This role designs, implements, and maintains security controls for Federal and DoD cloud environments, ensuring compliance with FedRAMP High, DoD IL5/IL6, and NIST SP 800-53. The engineer will operate security tooling (SIEM, EDR, vulnerability scanners), secure Kubernetes and Linux environments, and implement Zero Trust principles. Responsibilities include managing ATO packages, continuous monitoring, incident response, and collaborating with DevOps to build secure CI/CD pipelines.
This role builds the end-to-end billing and monetization infrastructure for consumer subscriptions like X Premium and SuperGrok. The engineer will design promotional offer systems, global payment methods, and intelligent communication systems to drive engagement and revenue. This position requires experience with large-scale backend systems, distributed systems, and a passion for revenue-generating products.
This role designs, programs, and commissions facility automation controls for a data center plant. Responsibilities include writing PLC code, building HMI/SCADA interfaces, integrating with BMS/EPMS systems, and ensuring safety compliance with NEC/NFPA standards. Requires 1+ years of experience in industrial controls or building automation, with proficiency in PLC programming and industrial protocols.
